Developing a Cost-Effectiveness Model of Digital Therapeutics for Smoking Cessation.

The purpose of this research was to construct a Markov model of digital therapeutics to predict the lifetime costs and consequences that would be incurred by a hypothetical group of adult smokers in Korea who only made a single attempt to stop smoking. To determine the efficacy of DTx, we created an annual cycle Markov model. The result shows that the NRT strategy is determined as the dominant strategy. Digital therapeutics acts as a complement to pharmacotherapy and is a low-cost option.

A Review of Current Digital Mental Health Care Applications for Anxiety Symptoms and Future Prospects.

OBJECTIVE: Since the impact of the coronavirus disease-2019 pandemic, the need for efficiency in medical services has become more urgent than ever. The digital treatment market is rapidly growing worldwide and digital therapeutics (DTx), a major part of the digital medical services, is also emerging as a new paradigm for treatment, with its industry growing rapidly as well. Increasing research is done on the effectiveness of mobile DTx in improving mental health conditions such as insomnia, panic, and depression. METHODS: This review paper investigates 1) the functions and characteristics of mobile digital mental health care applications for the treatment of anxiety symptoms, 2) extracts common attributes of the applications, and 3) compares them with existing traditional treatment mechanisms. RESULTS: Among the 20,000 mental health management applications that have been developed so far, 8 applications that are relatively widely used were selected and reviewed. Check-in, self-help tips, quick relief, journal, courses for practice are common features of the digital mental health care applications for anxiety and are also widely used feature in the cognitive behavioral therapy. CONCLUSION: Based on this review, we have proposed the essential elements and directions for the development of a Korean digital mental health care applications for anxiety disorders.

Comparison of AI with and without hand-crafted features to classify Alzheimer's disease in different languages.

BACKGROUND: Detecting and analyzing Alzheimer's disease (AD) in its early stages is a crucial and significant challenge. Speech data from AD patients can aid in diagnosing AD since the speech features have common patterns independent of race and spoken language. However, previous models for diagnosing AD from speech data have often focused on the characteristics of a single language, with no guarantee of scalability to other languages. In this study, we used the same method to extract acoustic features from two language datasets to diagnose AD. METHODS: Using the Korean and English speech datasets, we used ten models capable of real-time AD and healthy control classification, regardless of language type. Four machine learning models were based on hand-crafted features, while the remaining six deep learning models utilized non-explainable features. RESULTS: The highest accuracy achieved by the machine learning models was 0.73 and 0.69 for the Korean and English speech datasets, respectively. The deep learning models' maximum achievable accuracy reached 0.75 and 0.78, with their minimum classification time of 0.01s and 0.02s. These findings reveal the models' robustness regardless of Korean and English and real-time diagnosis of AD through a 30-s voice sample. CONCLUSION: Non-explainable deep learning models that directly acquire voice representations surpassed machine learning models utilizing hand-crafted features in AD diagnosis. In addition, these AI models could confirm the possibility of extending to a language-agnostic AD diagnosis.

Effects of bilateral tDCS over DLPFC on response inhibition, craving, and brain functional connectivity in Internet gaming disorder: A randomized, double-blind, sham-controlled trial with fMRI.

Background and aims: Impaired inhibitory control accompanied by enhanced craving is hallmark of addiction. This study investigated the effects of transcranial direct current stimulation (tDCS) on response inhibition and craving in Internet gaming disorder (IGD). We examined the brain changes after tDCS and their correlation with clinical variables. Methods: Twenty-four males with IGD were allocated randomly to an active or sham tDCS group, and data from 22 participants were included for analysis. Participants self-administered bilateral tDCS over the dorsolateral prefrontal cortex (DLPFC) for 10 sessions. Stop-signal tasks were conducted to measure response inhibition and participants were asked about their cravings for Internet gaming at baseline and post-tDCS. Functional magnetic resonance imaging data were collected at pre- and post-tDCS, and group differences in resting-state functional connectivity (rsFC) changes from the bilateral DLPFC and nucleus accumbens were examined. We explored the relationship between changes in the rsFC and behavioral variables in the active tDCS group. Results: A significant group-by-time interaction was observed in response inhibition. After tDCS, only the active group showed a decrease in the stop-signal reaction time (SSRT). Although craving decreased, there were no significant group-by-time interactions or group main effects. The anterior cingulate cortex (ACC) showed group differences in post- versus pre-tDCS rsFC from the right DLPFC. The rsFC between the ACC and left middle frontal gyrus was negatively correlated with the SSRT. Discussion and conclusion: Our study provides preliminary evidence that bilateral tDCS over the DLPFC improves inhibitory control and could serve as a therapeutic approach for IGD.

Decreased Serum Cocaine- and Amphetamine-Regulated Transcript Level in Internet Gaming Disorder.

OBJECTIVE: Vulnerability to internet gaming disorder (IGD) has increased as internet gaming continues to grow. Cocaine- and amphetamine-regulated transcript (CART) is a hormone that plays a role in reward, anxiety, and stress. The purpose of this study was to identify the role of CART in the pathophysiology of IGD. METHODS: The serum CART levels were measured by enzyme-linked immunosorbent assay, and the associations of the serum CART level with psychological variables were analyzed in patients with IGD (n=31) and healthy controls (HC) (n=42). RESULTS: The serum CART level was significantly lower in the IGD than HC group. The IGD group scored significantly higher than the HC group on the psychological domains of depression, anxiety, the reward response in the Behavioral Activation System and Behavioral Inhibition System. There were no significant correlations between serum CART level and other psychological variables in the IGD group. CONCLUSION: Our results indicate that a decrease in the expression of the serum CART level is associated with the vulnerability of developing IGD. This study supports the possibility that CART is a biomarker in the pathophysiology of IGD.

Development of depression detection algorithm using text scripts of routine psychiatric interview.

Background: A psychiatric interview is one of the important procedures in diagnosing psychiatric disorders. Through this interview, psychiatrists listen to the patient's medical history and major complaints, check their emotional state, and obtain clues for clinical diagnosis. Although there have been attempts to diagnose a specific mental disorder from a short doctor-patient conversation, there has been no attempt to classify the patient's emotional state based on the text scripts from a formal interview of more than 30 min and use it to diagnose depression. This study aimed to utilize the existing machine learning algorithm in diagnosing depression using the transcripts of one-on-one interviews between psychiatrists and depressed patients. Methods: Seventy-seven clinical patients [with depression (n = 60); without depression (n = 17)] with a prior psychiatric diagnosis history participated in this study. The study was conducted with 24 male and 53 female subjects with the mean age of 33.8 (± 3.0). Psychiatrists conducted a conversational interview with each patient that lasted at least 30 min. All interviews with the subjects between August 2021 and November 2022 were recorded and transcribed into text scripts, and a text emotion recognition module was used to indicate the subject's representative emotions of each sentence. A machine learning algorithm discriminates patients with depression and those without depression based on text scripts. Results: A machine learning model classified text scripts from depressive patients with non-depressive ones with an acceptable accuracy rate (AUC of 0.85). The distribution of emotions (surprise, fear, anger, love, sadness, disgust, neutral, and happiness) was significantly different between patients with depression and those without depression (p < 0.001), and the most contributing emotion in classifying the two groups was disgust (p < 0.001). Conclusion: This is a qualitative and retrospective study to develop a tool to detect depression against patients without depression based on the text scripts of psychiatric interview, suggesting a novel and practical approach to understand the emotional characteristics of depression patients and to use them to detect the diagnosis of depression based on machine learning methods. This model could assist psychiatrists in clinical settings who conduct routine conversations with patients using text transcripts of the interviews.

Validity and reliability of the Brazilian version of the Smartphone Addiction Scale-Short Version for university students and adult population / Validade e confiabilidade da versão Brasileira da Smartphone Addiction Scale-Short Version para estudantes universitários e adultos

This study sought evidence of the validity of the Smartphone Addiction Scale-Short Version for a Brazilian sample of 718 individuals, amongst university students (n = 387, M age = 22.1 years) and adults (n = 331, M age = 35.2 years), who completed a sociodemographic questionnaire and the scale. The transcultural adaptation was carried out using specific protocols as recommended by expert's committees. The factorial structure was evaluated by three methods: Confirmatory Factor Analysis, Principal Component Analysis, and Network Analysis. The adjustment parameters were not adequate and Principal Component Analysis explained 39.2% of the variance. The scale showed good reliability (α = 0.81) and a 39.4% prevalence of problematic phone use. The Network Analysis indicated that the correlations between the items were similar in the two populations. This is an unpublished study evaluating the usage pattern of smartphones in a sample of the adult population from all Brazilian states.

Este estudo buscou evidências de validade da Smartphone Addiction Scale-Short Version para uma amostra brasileira de 718 indivíduos, entre universitários (n = 387; Midade = 22,1 anos) e adultos (n = 331; Midade = 35,2 anos), que preencheram um questionário sociodemográfico e uma escala. Realizou-se a adaptação transcultural com protocolos específicos respondidos por juízes. A estrutura fatorial foi avaliada por três métodos: Análise Fatorial Confirmatória, Análise de Componentes Principais e Análise de Rede. Os parâmetros de ajustes não foram adequados e a Análise de Componentes Principais explicou 39,2% da variância. A escala mostrou boa confiabilidade (α = 0,81) e prevalência de 39,4% de uso problemático de smartphone. A Análise de Rede indicou que as correlações entre os itens foram parecidas nas duas populações. Este é um estudo inédito, avaliando o padrão de uso de smartphones em uma amostra da população adulta de todos os estados brasileiros.